{"id":"W4387770710","doi":"10.21203/rs.3.rs-3448044/v1","title":"Data Security and Privacy Research Trends: LDA Topic Modeling","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Computer science; Expansive; Data science; Encryption; Cloud computing; Internet privacy; Information privacy; The Internet; Computer security; World Wide Web; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.009560366,0.0003118855,0.0004176389,0.00246357,0.0007410477,0.001107546,0.007232063,0.0004792281,0.00002510269],"category_scores_gemma":[0.002576737,0.0003179389,0.0000768266,0.0025192,0.000289079,0.0008784716,0.05289092,0.005199735,0.00007295011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003970969,"about_ca_system_score_gemma":0.0005504783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008348284,"about_ca_topic_score_gemma":0.0002663881,"domain_scores_codex":[0.991434,0.001427245,0.0004860566,0.002510148,0.002835253,0.001307296],"domain_scores_gemma":[0.9905232,0.001016446,0.00008038083,0.006662046,0.001364926,0.0003530311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001710884,0.0007798829,0.001362212,0.008930791,0.0003250808,0.001537139,0.01471597,0.005452572,0.0009296468,0.09434881,0.07835875,0.7930881],"study_design_scores_gemma":[0.0001607653,0.0001656061,0.0002570644,0.0006397325,0.000002722239,0.00001053231,0.0002531865,0.655399,0.000504164,0.3262286,0.01600905,0.0003696042],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01521337,0.002130725,0.9613199,0.01169183,0.0007320968,0.002090629,0.0005545418,0.003638974,0.002627899],"genre_scores_gemma":[0.932641,0.004202232,0.05754071,0.00002936283,0.0007388721,0.000744834,0.0003571129,0.0001226144,0.003623247],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9174277,"threshold_uncertainty_score":0.9999294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4510731732612783,"score_gpt":0.5333456925675857,"score_spread":0.08227251930630741,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}